-
Notifications
You must be signed in to change notification settings - Fork 0
Feat: Implement garbage collection for s3 #49
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Merged
Merged
Changes from all commits
Commits
File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Some comments aren't visible on the classic Files Changed page.
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,93 @@ | ||
| package substrait | ||
|
|
||
| import ( | ||
| "context" | ||
| "fmt" | ||
| "opti-sql-go/config" | ||
| "time" | ||
|
|
||
| "github.com/minio/minio-go" | ||
| "github.com/redis/go-redis/v9" | ||
| "go.uber.org/zap" | ||
| ) | ||
|
|
||
| // garbage collection for removing files from s3 storage after expiration | ||
| var dontTouchTestFiles = []string{"country_full.csv", "userdata.parquet", "example.txt", "random_test"} | ||
|
|
||
| const ignoreFolder = "result-file-cache" | ||
| const loggerPrefix = "Garbage-Collection" | ||
| const waitTime = time.Second * 5 | ||
|
|
||
| func garbageCollection() { | ||
| logger := config.GetLogger() | ||
| logger.Info(fmt.Sprintf("[%v]starting garbage collection, won't touch these files %v", loggerPrefix, dontTouchTestFiles)) | ||
| config := config.GetConfig() | ||
| redisInstance := redis.NewClient(&redis.Options{ | ||
| Addr: config.Server.RedisAddr + ":6379", | ||
| Password: "", // no password | ||
| DB: 0, // use default DB | ||
| Protocol: 2, | ||
| }) | ||
| secretes := config.Secretes | ||
| accessKey := secretes.AccessKey | ||
| secretKey := secretes.SecretKey | ||
| endpoint := secretes.EndpointURL | ||
| bucket := secretes.BucketName | ||
| useSSL := true | ||
|
|
||
| client, err := minio.New(endpoint, accessKey, secretKey, useSSL) | ||
| if err != nil { | ||
| logger.Fatal("failed to construct s3 client to delete old files", zap.String("error message", fmt.Sprintf("%v", err))) | ||
| } | ||
| var failedAttempts = 0 | ||
| for { | ||
| start: | ||
| if failedAttempts > 5 { | ||
| logger.Warn("removing files has failed over 5 times, check redis and s3 for issues !!!") | ||
| } | ||
|
Rich-T-kid marked this conversation as resolved.
|
||
| fmt.Printf("waiting %v minutes before check for files to clear from s3", waitTime.Minutes()) | ||
| time.Sleep(waitTime) | ||
| start := time.Now() | ||
| entries, err := redisInstance.LRange(context.TODO(), ignoreFolder, 0, -1).Result() | ||
| if err != nil { | ||
| logger.Error(fmt.Sprintf("failed to read in files from %v", ignoreFolder), zap.Int("fail counter", failedAttempts)) | ||
| failedAttempts++ | ||
| goto start // try again | ||
| } | ||
| // read all the files in s3 | ||
| doneChan := make(chan struct{}) | ||
| readCount := 0 | ||
| var nonValidFiles []string | ||
| validMap := buildMap(dontTouchTestFiles, entries) | ||
| for fileName := range client.ListObjects(bucket, "", true, doneChan) { | ||
|
Rich-T-kid marked this conversation as resolved.
|
||
| if !validMap[fileName.Key] { | ||
| nonValidFiles = append(nonValidFiles, fileName.Key) | ||
| } | ||
| readCount++ | ||
| } | ||
| var removedFiles = 0 | ||
| for _, invalidFile := range nonValidFiles { | ||
| err := client.RemoveObject(bucket, invalidFile) | ||
| if err != nil { | ||
| logger.Warn(fmt.Sprintf("error removing %v from s3: %v", invalidFile, err)) | ||
| // log and move on | ||
| } else { | ||
| removedFiles++ | ||
| } | ||
| } | ||
| failedAttempts = 0 // reset failed attempts back to zero | ||
| logger.Info("Garbage Collection metrics", zap.Any("to-keep map", validMap), zap.Int("total-files count", readCount), zap.Int("removed-files count", removedFiles), zap.Any("time-taken", time.Since(start))) | ||
|
|
||
| } | ||
|
|
||
| } | ||
| func buildMap(source1 []string, source2 []string) map[string]bool { | ||
| result := make(map[string]bool) | ||
| for _, k := range source1 { | ||
| result[k] = true | ||
| } | ||
| for _, k := range source2 { | ||
| result[k] = true | ||
| } | ||
| return result | ||
| } | ||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Uh oh!
There was an error while loading. Please reload this page.